-
-
Notifications
You must be signed in to change notification settings - Fork 218
/
reader.rs
2633 lines (2479 loc) · 87.8 KB
/
reader.rs
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
use std::fs::File;
use std::io::{self, BufRead, Seek};
use std::marker::PhantomData;
use std::path::Path;
use std::result;
use csv_core::{Reader as CoreReader, ReaderBuilder as CoreReaderBuilder};
use serde::de::DeserializeOwned;
use crate::byte_record::{ByteRecord, Position};
use crate::error::{Error, ErrorKind, Result, Utf8Error};
use crate::string_record::StringRecord;
use crate::{Terminator, Trim};
/// Builds a CSV reader with various configuration knobs.
///
/// This builder can be used to tweak the field delimiter, record terminator
/// and more. Once a CSV `Reader` is built, its configuration cannot be
/// changed.
#[derive(Debug)]
pub struct ReaderBuilder {
capacity: usize,
flexible: bool,
has_headers: bool,
trim: Trim,
/// The underlying CSV parser builder.
///
/// We explicitly put this on the heap because CoreReaderBuilder embeds an
/// entire DFA transition table, which along with other things, tallies up
/// to almost 500 bytes on the stack.
builder: Box<CoreReaderBuilder>,
}
impl Default for ReaderBuilder {
fn default() -> ReaderBuilder {
ReaderBuilder {
capacity: 8 * (1 << 10),
flexible: false,
has_headers: true,
trim: Trim::default(),
builder: Box::new(CoreReaderBuilder::default()),
}
}
}
impl ReaderBuilder {
/// Create a new builder for configuring CSV parsing.
///
/// To convert a builder into a reader, call one of the methods starting
/// with `from_`.
///
/// # Example
///
/// ```
/// use std::error::Error;
/// use csv::{ReaderBuilder, StringRecord};
///
/// # fn main() { example().unwrap(); }
/// fn example() -> Result<(), Box<dyn Error>> {
/// let data = "\
/// city,country,pop
/// Boston,United States,4628910
/// Concord,United States,42695
/// ";
/// let mut rdr = ReaderBuilder::new().from_reader(data.as_bytes());
///
/// let records = rdr
/// .records()
/// .collect::<Result<Vec<StringRecord>, csv::Error>>()?;
/// assert_eq!(records, vec![
/// vec!["Boston", "United States", "4628910"],
/// vec!["Concord", "United States", "42695"],
/// ]);
/// Ok(())
/// }
/// ```
pub fn new() -> ReaderBuilder {
ReaderBuilder::default()
}
/// Build a CSV parser from this configuration that reads data from the
/// given file path.
///
/// If there was a problem opening the file at the given path, then this
/// returns the corresponding error.
///
/// # Example
///
/// ```no_run
/// use std::error::Error;
/// use csv::ReaderBuilder;
///
/// # fn main() { example().unwrap(); }
/// fn example() -> Result<(), Box<dyn Error>> {
/// let mut rdr = ReaderBuilder::new().from_path("foo.csv")?;
/// for result in rdr.records() {
/// let record = result?;
/// println!("{:?}", record);
/// }
/// Ok(())
/// }
/// ```
pub fn from_path<P: AsRef<Path>>(&self, path: P) -> Result<Reader<File>> {
Ok(Reader::new(self, File::open(path)?))
}
/// Build a CSV parser from this configuration that reads data from `rdr`.
///
/// Note that the CSV reader is buffered automatically, so you should not
/// wrap `rdr` in a buffered reader like `io::BufReader`.
///
/// # Example
///
/// ```
/// use std::error::Error;
/// use csv::ReaderBuilder;
///
/// # fn main() { example().unwrap(); }
/// fn example() -> Result<(), Box<dyn Error>> {
/// let data = "\
/// city,country,pop
/// Boston,United States,4628910
/// Concord,United States,42695
/// ";
/// let mut rdr = ReaderBuilder::new().from_reader(data.as_bytes());
/// for result in rdr.records() {
/// let record = result?;
/// println!("{:?}", record);
/// }
/// Ok(())
/// }
/// ```
pub fn from_reader<R: io::Read>(&self, rdr: R) -> Reader<R> {
Reader::new(self, rdr)
}
/// The field delimiter to use when parsing CSV.
///
/// The default is `b','`.
///
/// # Example
///
/// ```
/// use std::error::Error;
/// use csv::ReaderBuilder;
///
/// # fn main() { example().unwrap(); }
/// fn example() -> Result<(), Box<dyn Error>> {
/// let data = "\
/// city;country;pop
/// Boston;United States;4628910
/// ";
/// let mut rdr = ReaderBuilder::new()
/// .delimiter(b';')
/// .from_reader(data.as_bytes());
///
/// if let Some(result) = rdr.records().next() {
/// let record = result?;
/// assert_eq!(record, vec!["Boston", "United States", "4628910"]);
/// Ok(())
/// } else {
/// Err(From::from("expected at least one record but got none"))
/// }
/// }
/// ```
pub fn delimiter(&mut self, delimiter: u8) -> &mut ReaderBuilder {
self.builder.delimiter(delimiter);
self
}
/// Whether to treat the first row as a special header row.
///
/// By default, the first row is treated as a special header row, which
/// means the header is never returned by any of the record reading methods
/// or iterators. When this is disabled (`yes` set to `false`), the first
/// row is not treated specially.
///
/// Note that the `headers` and `byte_headers` methods are unaffected by
/// whether this is set. Those methods always return the first record.
///
/// # Example
///
/// This example shows what happens when `has_headers` is disabled.
/// Namely, the first row is treated just like any other row.
///
/// ```
/// use std::error::Error;
/// use csv::ReaderBuilder;
///
/// # fn main() { example().unwrap(); }
/// fn example() -> Result<(), Box<dyn Error>> {
/// let data = "\
/// city,country,pop
/// Boston,United States,4628910
/// ";
/// let mut rdr = ReaderBuilder::new()
/// .has_headers(false)
/// .from_reader(data.as_bytes());
/// let mut iter = rdr.records();
///
/// // Read the first record.
/// if let Some(result) = iter.next() {
/// let record = result?;
/// assert_eq!(record, vec!["city", "country", "pop"]);
/// } else {
/// return Err(From::from(
/// "expected at least two records but got none"));
/// }
///
/// // Read the second record.
/// if let Some(result) = iter.next() {
/// let record = result?;
/// assert_eq!(record, vec!["Boston", "United States", "4628910"]);
/// } else {
/// return Err(From::from(
/// "expected at least two records but got one"))
/// }
/// Ok(())
/// }
/// ```
pub fn has_headers(&mut self, yes: bool) -> &mut ReaderBuilder {
self.has_headers = yes;
self
}
/// Whether the number of fields in records is allowed to change or not.
///
/// When disabled (which is the default), parsing CSV data will return an
/// error if a record is found with a number of fields different from the
/// number of fields in a previous record.
///
/// When enabled, this error checking is turned off.
///
/// # Example: flexible records enabled
///
/// ```
/// use std::error::Error;
/// use csv::ReaderBuilder;
///
/// # fn main() { example().unwrap(); }
/// fn example() -> Result<(), Box<dyn Error>> {
/// // Notice that the first row is missing the population count.
/// let data = "\
/// city,country,pop
/// Boston,United States
/// ";
/// let mut rdr = ReaderBuilder::new()
/// .flexible(true)
/// .from_reader(data.as_bytes());
///
/// if let Some(result) = rdr.records().next() {
/// let record = result?;
/// assert_eq!(record, vec!["Boston", "United States"]);
/// Ok(())
/// } else {
/// Err(From::from("expected at least one record but got none"))
/// }
/// }
/// ```
///
/// # Example: flexible records disabled
///
/// This shows the error that appears when records of unequal length
/// are found and flexible records have been disabled (which is the
/// default).
///
/// ```
/// use std::error::Error;
/// use csv::{ErrorKind, ReaderBuilder};
///
/// # fn main() { example().unwrap(); }
/// fn example() -> Result<(), Box<dyn Error>> {
/// // Notice that the first row is missing the population count.
/// let data = "\
/// city,country,pop
/// Boston,United States
/// ";
/// let mut rdr = ReaderBuilder::new()
/// .flexible(false)
/// .from_reader(data.as_bytes());
///
/// if let Some(Err(err)) = rdr.records().next() {
/// match *err.kind() {
/// ErrorKind::UnequalLengths { expected_len, len, .. } => {
/// // The header row has 3 fields...
/// assert_eq!(expected_len, 3);
/// // ... but the first row has only 2 fields.
/// assert_eq!(len, 2);
/// Ok(())
/// }
/// ref wrong => {
/// Err(From::from(format!(
/// "expected UnequalLengths error but got {:?}",
/// wrong)))
/// }
/// }
/// } else {
/// Err(From::from(
/// "expected at least one errored record but got none"))
/// }
/// }
/// ```
pub fn flexible(&mut self, yes: bool) -> &mut ReaderBuilder {
self.flexible = yes;
self
}
/// Whether fields are trimmed of leading and trailing whitespace or not.
///
/// By default, no trimming is performed. This method permits one to
/// override that behavior and choose one of the following options:
///
/// 1. `Trim::Headers` trims only header values.
/// 2. `Trim::Fields` trims only non-header or "field" values.
/// 3. `Trim::All` trims both header and non-header values.
///
/// A value is only interpreted as a header value if this CSV reader is
/// configured to read a header record (which is the default).
///
/// When reading string records, characters meeting the definition of
/// Unicode whitespace are trimmed. When reading byte records, characters
/// meeting the definition of ASCII whitespace are trimmed. ASCII
/// whitespace characters correspond to the set `[\t\n\v\f\r ]`.
///
/// # Example
///
/// This example shows what happens when all values are trimmed.
///
/// ```
/// use std::error::Error;
/// use csv::{ReaderBuilder, StringRecord, Trim};
///
/// # fn main() { example().unwrap(); }
/// fn example() -> Result<(), Box<dyn Error>> {
/// let data = "\
/// city , country , pop
/// Boston,\"
/// United States\",4628910
/// Concord, United States ,42695
/// ";
/// let mut rdr = ReaderBuilder::new()
/// .trim(Trim::All)
/// .from_reader(data.as_bytes());
/// let records = rdr
/// .records()
/// .collect::<Result<Vec<StringRecord>, csv::Error>>()?;
/// assert_eq!(records, vec![
/// vec!["Boston", "United States", "4628910"],
/// vec!["Concord", "United States", "42695"],
/// ]);
/// Ok(())
/// }
/// ```
pub fn trim(&mut self, trim: Trim) -> &mut ReaderBuilder {
self.trim = trim;
self
}
/// The record terminator to use when parsing CSV.
///
/// A record terminator can be any single byte. The default is a special
/// value, `Terminator::CRLF`, which treats any occurrence of `\r`, `\n`
/// or `\r\n` as a single record terminator.
///
/// # Example: `$` as a record terminator
///
/// ```
/// use std::error::Error;
/// use csv::{ReaderBuilder, Terminator};
///
/// # fn main() { example().unwrap(); }
/// fn example() -> Result<(), Box<dyn Error>> {
/// let data = "city,country,pop$Boston,United States,4628910";
/// let mut rdr = ReaderBuilder::new()
/// .terminator(Terminator::Any(b'$'))
/// .from_reader(data.as_bytes());
///
/// if let Some(result) = rdr.records().next() {
/// let record = result?;
/// assert_eq!(record, vec!["Boston", "United States", "4628910"]);
/// Ok(())
/// } else {
/// Err(From::from("expected at least one record but got none"))
/// }
/// }
/// ```
pub fn terminator(&mut self, term: Terminator) -> &mut ReaderBuilder {
self.builder.terminator(term.to_core());
self
}
/// The quote character to use when parsing CSV.
///
/// The default is `b'"'`.
///
/// # Example: single quotes instead of double quotes
///
/// ```
/// use std::error::Error;
/// use csv::ReaderBuilder;
///
/// # fn main() { example().unwrap(); }
/// fn example() -> Result<(), Box<dyn Error>> {
/// let data = "\
/// city,country,pop
/// Boston,'United States',4628910
/// ";
/// let mut rdr = ReaderBuilder::new()
/// .quote(b'\'')
/// .from_reader(data.as_bytes());
///
/// if let Some(result) = rdr.records().next() {
/// let record = result?;
/// assert_eq!(record, vec!["Boston", "United States", "4628910"]);
/// Ok(())
/// } else {
/// Err(From::from("expected at least one record but got none"))
/// }
/// }
/// ```
pub fn quote(&mut self, quote: u8) -> &mut ReaderBuilder {
self.builder.quote(quote);
self
}
/// The escape character to use when parsing CSV.
///
/// In some variants of CSV, quotes are escaped using a special escape
/// character like `\` (instead of escaping quotes by doubling them).
///
/// By default, recognizing these idiosyncratic escapes is disabled.
///
/// # Example
///
/// ```
/// use std::error::Error;
/// use csv::ReaderBuilder;
///
/// # fn main() { example().unwrap(); }
/// fn example() -> Result<(), Box<dyn Error>> {
/// let data = "\
/// city,country,pop
/// Boston,\"The \\\"United\\\" States\",4628910
/// ";
/// let mut rdr = ReaderBuilder::new()
/// .escape(Some(b'\\'))
/// .from_reader(data.as_bytes());
///
/// if let Some(result) = rdr.records().next() {
/// let record = result?;
/// assert_eq!(record, vec![
/// "Boston", "The \"United\" States", "4628910",
/// ]);
/// Ok(())
/// } else {
/// Err(From::from("expected at least one record but got none"))
/// }
/// }
/// ```
pub fn escape(&mut self, escape: Option<u8>) -> &mut ReaderBuilder {
self.builder.escape(escape);
self
}
/// Enable double quote escapes.
///
/// This is enabled by default, but it may be disabled. When disabled,
/// doubled quotes are not interpreted as escapes.
///
/// # Example
///
/// ```
/// use std::error::Error;
/// use csv::ReaderBuilder;
///
/// # fn main() { example().unwrap(); }
/// fn example() -> Result<(), Box<dyn Error>> {
/// let data = "\
/// city,country,pop
/// Boston,\"The \"\"United\"\" States\",4628910
/// ";
/// let mut rdr = ReaderBuilder::new()
/// .double_quote(false)
/// .from_reader(data.as_bytes());
///
/// if let Some(result) = rdr.records().next() {
/// let record = result?;
/// assert_eq!(record, vec![
/// "Boston", "The \"United\"\" States\"", "4628910",
/// ]);
/// Ok(())
/// } else {
/// Err(From::from("expected at least one record but got none"))
/// }
/// }
/// ```
pub fn double_quote(&mut self, yes: bool) -> &mut ReaderBuilder {
self.builder.double_quote(yes);
self
}
/// Enable or disable quoting.
///
/// This is enabled by default, but it may be disabled. When disabled,
/// quotes are not treated specially.
///
/// # Example
///
/// ```
/// use std::error::Error;
/// use csv::ReaderBuilder;
///
/// # fn main() { example().unwrap(); }
/// fn example() -> Result<(), Box<dyn Error>> {
/// let data = "\
/// city,country,pop
/// Boston,\"The United States,4628910
/// ";
/// let mut rdr = ReaderBuilder::new()
/// .quoting(false)
/// .from_reader(data.as_bytes());
///
/// if let Some(result) = rdr.records().next() {
/// let record = result?;
/// assert_eq!(record, vec![
/// "Boston", "\"The United States", "4628910",
/// ]);
/// Ok(())
/// } else {
/// Err(From::from("expected at least one record but got none"))
/// }
/// }
/// ```
pub fn quoting(&mut self, yes: bool) -> &mut ReaderBuilder {
self.builder.quoting(yes);
self
}
/// The comment character to use when parsing CSV.
///
/// If the start of a record begins with the byte given here, then that
/// line is ignored by the CSV parser.
///
/// This is disabled by default.
///
/// # Example
///
/// ```
/// use std::error::Error;
/// use csv::ReaderBuilder;
///
/// # fn main() { example().unwrap(); }
/// fn example() -> Result<(), Box<dyn Error>> {
/// let data = "\
/// city,country,pop
/// #Concord,United States,42695
/// Boston,United States,4628910
/// ";
/// let mut rdr = ReaderBuilder::new()
/// .comment(Some(b'#'))
/// .from_reader(data.as_bytes());
///
/// if let Some(result) = rdr.records().next() {
/// let record = result?;
/// assert_eq!(record, vec!["Boston", "United States", "4628910"]);
/// Ok(())
/// } else {
/// Err(From::from("expected at least one record but got none"))
/// }
/// }
/// ```
pub fn comment(&mut self, comment: Option<u8>) -> &mut ReaderBuilder {
self.builder.comment(comment);
self
}
/// A convenience method for specifying a configuration to read ASCII
/// delimited text.
///
/// This sets the delimiter and record terminator to the ASCII unit
/// separator (`\x1F`) and record separator (`\x1E`), respectively.
///
/// # Example
///
/// ```
/// use std::error::Error;
/// use csv::ReaderBuilder;
///
/// # fn main() { example().unwrap(); }
/// fn example() -> Result<(), Box<dyn Error>> {
/// let data = "\
/// city\x1Fcountry\x1Fpop\x1EBoston\x1FUnited States\x1F4628910";
/// let mut rdr = ReaderBuilder::new()
/// .ascii()
/// .from_reader(data.as_bytes());
///
/// if let Some(result) = rdr.records().next() {
/// let record = result?;
/// assert_eq!(record, vec!["Boston", "United States", "4628910"]);
/// Ok(())
/// } else {
/// Err(From::from("expected at least one record but got none"))
/// }
/// }
/// ```
pub fn ascii(&mut self) -> &mut ReaderBuilder {
self.builder.ascii();
self
}
/// Set the capacity (in bytes) of the buffer used in the CSV reader.
/// This defaults to a reasonable setting.
pub fn buffer_capacity(&mut self, capacity: usize) -> &mut ReaderBuilder {
self.capacity = capacity;
self
}
/// Enable or disable the NFA for parsing CSV.
///
/// This is intended to be a debug option. The NFA is always slower than
/// the DFA.
#[doc(hidden)]
pub fn nfa(&mut self, yes: bool) -> &mut ReaderBuilder {
self.builder.nfa(yes);
self
}
}
/// A already configured CSV reader.
///
/// A CSV reader takes as input CSV data and transforms that into standard Rust
/// values. The most flexible way to read CSV data is as a sequence of records,
/// where a record is a sequence of fields and each field is a string. However,
/// a reader can also deserialize CSV data into Rust types like `i64` or
/// `(String, f64, f64, f64)` or even a custom struct automatically using
/// Serde.
///
/// # Configuration
///
/// A CSV reader has a couple convenient constructor methods like `from_path`
/// and `from_reader`. However, if you want to configure the CSV reader to use
/// a different delimiter or quote character (among many other things), then
/// you should use a [`ReaderBuilder`](struct.ReaderBuilder.html) to construct
/// a `Reader`. For example, to change the field delimiter:
///
/// ```
/// use std::error::Error;
/// use csv::ReaderBuilder;
///
/// # fn main() { example().unwrap(); }
/// fn example() -> Result<(), Box<dyn Error>> {
/// let data = "\
/// city;country;pop
/// Boston;United States;4628910
/// ";
/// let mut rdr = ReaderBuilder::new()
/// .delimiter(b';')
/// .from_reader(data.as_bytes());
///
/// if let Some(result) = rdr.records().next() {
/// let record = result?;
/// assert_eq!(record, vec!["Boston", "United States", "4628910"]);
/// Ok(())
/// } else {
/// Err(From::from("expected at least one record but got none"))
/// }
/// }
/// ```
///
/// # Error handling
///
/// In general, CSV *parsing* does not ever return an error. That is, there is
/// no such thing as malformed CSV data. Instead, this reader will prioritize
/// finding a parse over rejecting CSV data that it does not understand. This
/// choice was inspired by other popular CSV parsers, but also because it is
/// pragmatic. CSV data varies wildly, so even if the CSV data is malformed,
/// it might still be possible to work with the data. In the land of CSV, there
/// is no "right" or "wrong," only "right" and "less right."
///
/// With that said, a number of errors can occur while reading CSV data:
///
/// * By default, all records in CSV data must have the same number of fields.
/// If a record is found with a different number of fields than a prior
/// record, then an error is returned. This behavior can be disabled by
/// enabling flexible parsing via the `flexible` method on
/// [`ReaderBuilder`](struct.ReaderBuilder.html).
/// * When reading CSV data from a resource (like a file), it is possible for
/// reading from the underlying resource to fail. This will return an error.
/// For subsequent calls to the `Reader` after encountering a such error
/// (unless `seek` is used), it will behave as if end of file had been
/// reached, in order to avoid running into infinite loops when still
/// attempting to read the next record when one has errored.
/// * When reading CSV data into `String` or `&str` fields (e.g., via a
/// [`StringRecord`](struct.StringRecord.html)), UTF-8 is strictly
/// enforced. If CSV data is invalid UTF-8, then an error is returned. If
/// you want to read invalid UTF-8, then you should use the byte oriented
/// APIs such as [`ByteRecord`](struct.ByteRecord.html). If you need explicit
/// support for another encoding entirely, then you'll need to use another
/// crate to transcode your CSV data to UTF-8 before parsing it.
/// * When using Serde to deserialize CSV data into Rust types, it is possible
/// for a number of additional errors to occur. For example, deserializing
/// a field `xyz` into an `i32` field will result in an error.
///
/// For more details on the precise semantics of errors, see the
/// [`Error`](enum.Error.html) type.
#[derive(Debug)]
pub struct Reader<R> {
/// The underlying CSV parser.
///
/// We explicitly put this on the heap because CoreReader embeds an entire
/// DFA transition table, which along with other things, tallies up to
/// almost 500 bytes on the stack.
core: Box<CoreReader>,
/// The underlying reader.
rdr: io::BufReader<R>,
/// Various state tracking.
///
/// There is more state embedded in the `CoreReader`.
state: ReaderState,
}
#[derive(Debug)]
struct ReaderState {
/// When set, this contains the first row of any parsed CSV data.
///
/// This is always populated, regardless of whether `has_headers` is set.
headers: Option<Headers>,
/// When set, the first row of parsed CSV data is excluded from things
/// that read records, like iterators and `read_record`.
has_headers: bool,
/// When set, there is no restriction on the length of records. When not
/// set, every record must have the same number of fields, or else an error
/// is reported.
flexible: bool,
trim: Trim,
/// The number of fields in the first record parsed.
first_field_count: Option<u64>,
/// The current position of the parser.
///
/// Note that this position is only observable by callers at the start
/// of a record. More granular positions are not supported.
cur_pos: Position,
/// Whether the first record has been read or not.
first: bool,
/// Whether the reader has been seeked or not.
seeked: bool,
/// Whether EOF of the underlying reader has been reached or not.
///
/// IO errors on the underlying reader will be considered as an EOF for
/// subsequent read attempts, as it would be incorrect to keep on trying
/// to read when the underlying reader has broken.
///
/// For clarity, having the best `Debug` impl and in case they need to be
/// treated differently at some point, we store whether the `EOF` is
/// considered because an actual EOF happened, or because we encoundered
/// an IO error.
/// This has no additional runtime cost.
eof: ReaderEofState,
}
/// Whether EOF of the underlying reader has been reached or not.
///
/// IO errors on the underlying reader will be considered as an EOF for
/// subsequent read attempts, as it would be incorrect to keep on trying
/// to read when the underlying reader has broken.
///
/// For clarity, having the best `Debug` impl and in case they need to be
/// treated differently at some point, we store whether the `EOF` is
/// considered because an actual EOF happened, or because we encoundered
/// an IO error
#[derive(Debug, Clone, Copy, PartialEq, Eq)]
enum ReaderEofState {
NotEof,
Eof,
IOError,
}
/// Headers encapsulates any data associated with the headers of CSV data.
///
/// The headers always correspond to the first row.
#[derive(Debug)]
struct Headers {
/// The header, as raw bytes.
byte_record: ByteRecord,
/// The header, as valid UTF-8 (or a UTF-8 error).
string_record: result::Result<StringRecord, Utf8Error>,
}
impl Reader<Reader<File>> {
/// Create a new CSV parser with a default configuration for the given
/// file path.
///
/// To customize CSV parsing, use a `ReaderBuilder`.
///
/// # Example
///
/// ```no_run
/// use std::error::Error;
/// use csv::Reader;
///
/// # fn main() { example().unwrap(); }
/// fn example() -> Result<(), Box<dyn Error>> {
/// let mut rdr = Reader::from_path("foo.csv")?;
/// for result in rdr.records() {
/// let record = result?;
/// println!("{:?}", record);
/// }
/// Ok(())
/// }
/// ```
pub fn from_path<P: AsRef<Path>>(path: P) -> Result<Reader<File>> {
ReaderBuilder::new().from_path(path)
}
}
impl<R: io::Read> Reader<R> {
/// Create a new CSV reader given a builder and a source of underlying
/// bytes.
fn new(builder: &ReaderBuilder, rdr: R) -> Reader<R> {
Reader {
core: Box::new(builder.builder.build()),
rdr: io::BufReader::with_capacity(builder.capacity, rdr),
state: ReaderState {
headers: None,
has_headers: builder.has_headers,
flexible: builder.flexible,
trim: builder.trim,
first_field_count: None,
cur_pos: Position::new(),
first: false,
seeked: false,
eof: ReaderEofState::NotEof,
},
}
}
/// Create a new CSV parser with a default configuration for the given
/// reader.
///
/// To customize CSV parsing, use a `ReaderBuilder`.
///
/// # Example
///
/// ```
/// use std::error::Error;
/// use csv::Reader;
///
/// # fn main() { example().unwrap(); }
/// fn example() -> Result<(), Box<dyn Error>> {
/// let data = "\
/// city,country,pop
/// Boston,United States,4628910
/// Concord,United States,42695
/// ";
/// let mut rdr = Reader::from_reader(data.as_bytes());
/// for result in rdr.records() {
/// let record = result?;
/// println!("{:?}", record);
/// }
/// Ok(())
/// }
/// ```
pub fn from_reader(rdr: R) -> Reader<R> {
ReaderBuilder::new().from_reader(rdr)
}
/// Returns a borrowed iterator over deserialized records.
///
/// Each item yielded by this iterator is a `Result<D, Error>`.
/// Therefore, in order to access the record, callers must handle the
/// possibility of error (typically with `try!` or `?`).
///
/// If `has_headers` was enabled via a `ReaderBuilder` (which is the
/// default), then this does not include the first record. Additionally,
/// if `has_headers` is enabled, then deserializing into a struct will
/// automatically align the values in each row to the fields of a struct
/// based on the header row.
///
/// # Example
///
/// This shows how to deserialize CSV data into normal Rust structs. The
/// fields of the header row are used to match up the values in each row
/// to the fields of the struct.
///
/// ```
/// use std::error::Error;
///
/// use csv::Reader;
/// use serde::Deserialize;
///
/// #[derive(Debug, Deserialize, Eq, PartialEq)]
/// struct Row {
/// city: String,
/// country: String,
/// #[serde(rename = "popcount")]
/// population: u64,
/// }
///
/// # fn main() { example().unwrap(); }
/// fn example() -> Result<(), Box<dyn Error>> {
/// let data = "\
/// city,country,popcount
/// Boston,United States,4628910
/// ";
/// let mut rdr = Reader::from_reader(data.as_bytes());
/// let mut iter = rdr.deserialize();
///
/// if let Some(result) = iter.next() {
/// let record: Row = result?;
/// assert_eq!(record, Row {
/// city: "Boston".to_string(),
/// country: "United States".to_string(),
/// population: 4628910,
/// });
/// Ok(())
/// } else {
/// Err(From::from("expected at least one record but got none"))
/// }
/// }
/// ```
///
/// # Rules
///
/// For the most part, any Rust type that maps straight-forwardly to a CSV
/// record is supported. This includes maps, structs, tuples and tuple
/// structs. Other Rust types, such as `Vec`s, arrays, and enums have
/// a more complicated story. In general, when working with CSV data, one
/// should avoid *nested sequences* as much as possible.
///
/// Maps, structs, tuples and tuple structs map to CSV records in a simple
/// way. Tuples and tuple structs decode their fields in the order that
/// they are defined. Structs will do the same only if `has_headers` has
/// been disabled using [`ReaderBuilder`](struct.ReaderBuilder.html),
/// otherwise, structs and maps are deserialized based on the fields
/// defined in the header row. (If there is no header row, then
/// deserializing into a map will result in an error.)
///
/// Nested sequences are supported in a limited capacity. Namely, they
/// are flattened. As a result, it's often useful to use a `Vec` to capture
/// a "tail" of fields in a record:
///
/// ```
/// use std::error::Error;
///
/// use csv::ReaderBuilder;
/// use serde::Deserialize;
///
/// #[derive(Debug, Deserialize, Eq, PartialEq)]
/// struct Row {
/// label: String,
/// values: Vec<i32>,
/// }
///
/// # fn main() { example().unwrap(); }
/// fn example() -> Result<(), Box<dyn Error>> {
/// let data = "foo,1,2,3";
/// let mut rdr = ReaderBuilder::new()
/// .has_headers(false)
/// .from_reader(data.as_bytes());
/// let mut iter = rdr.deserialize();
///
/// if let Some(result) = iter.next() {
/// let record: Row = result?;
/// assert_eq!(record, Row {
/// label: "foo".to_string(),
/// values: vec![1, 2, 3],
/// });
/// Ok(())
/// } else {
/// Err(From::from("expected at least one record but got none"))
/// }
/// }
/// ```
///
/// In the above example, adding another field to the `Row` struct after
/// the `values` field will result in a deserialization error. This is
/// because the deserializer doesn't know when to stop reading fields
/// into the `values` vector, so it will consume the rest of the fields in
/// the record leaving none left over for the additional field.
///
/// Finally, simple enums in Rust can be deserialized as well. Namely,
/// enums must either be variants with no arguments or variants with a
/// single argument. Variants with no arguments are deserialized based on
/// which variant name the field matches. Variants with a single argument
/// are deserialized based on which variant can store the data. The latter
/// is only supported when using "untagged" enum deserialization. The
/// following example shows both forms in action:
///
/// ```
/// use std::error::Error;
///
/// use csv::Reader;
/// use serde::Deserialize;
///
/// #[derive(Debug, Deserialize, PartialEq)]
/// struct Row {
/// label: Label,
/// value: Number,
/// }
///